Timeline for How does SGD escape local minima?
Current License: CC BY-SA 4.0
Post Revisions
14 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 9 at 1:09 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Oct 12, 2025 at 1:03 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Jun 14, 2025 at 0:16 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Feb 14, 2025 at 0:05 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Oct 17, 2024 at 0:03 | history | bumped | CommunityBot | This question has answers that may be good or bad; the system has marked it active so that they can be reviewed. | |
| Sep 16, 2024 at 23:47 | answer | added | talles | timeline score: 0 | |
| Jun 3, 2020 at 10:54 | comment | added | stoic-santiago | @nbro One of the quizzes in here claim my question's opening statement. coursera.org/learn/getting-started-with-tensor-flow2 Also, it'd be great if you could go through that paper when you have the time and write an answer based upon it! :) | |
| Jun 2, 2020 at 15:41 | history | edited | nbro | CC BY-SA 4.0 |
added 1 character in body
|
| Jun 2, 2020 at 15:41 | comment | added | nbro |
Anyway, can you please provide the link to the exact Coursera's lecture that claims that? Also, if you want, later, I could read that paper and try to provide an answer based on it. And don't forget to tag me with @nbro next time, so that I see the comment ;)
|
|
| Jun 2, 2020 at 15:38 | comment | added | nbro | @cogito_ai I wouldn't say that SGD can't really escape local minima, but that it can get stuck in other (better?) minima. It's not like simulated annealing, where sometimes you perform a random action to escape local minima. However, it's true that there's some form of stochasticity in SGD that probably helps to explore more the search space. And that's what people probably mean by that sentence. See also ai.stackexchange.com/a/20380/2444. | |
| Jun 2, 2020 at 11:08 | comment | added | stoic-santiago | The statement above is from a MOOC on Coursera, while I found more details here - proceedings.mlr.press/v80/kleinberg18a/kleinberg18a.pdf | |
| Jun 2, 2020 at 10:30 | comment | added | nbro | Where did you read that SGD is able to escape local minima? | |
| May 31, 2020 at 10:18 | comment | added | Kaivalya Swami | This is a popular question. You can find a good explanation in the answer here. | |
| May 31, 2020 at 9:56 | history | asked | stoic-santiago | CC BY-SA 4.0 |